# Question 1
import pandas as pd 
pingees = pd.read_csv("https://raw.githubusercontent.com/mwaskom/seaborn-data/master/penguins.csv")
pingees

# Question 1

# Code directly imported from Chatgpt:

import plotly.express as px
import plotly.graph_objects as go
import seaborn as sns
import numpy as np

# Load the penguins dataset
penguins = sns.load_dataset("penguins")

# Drop rows with missing values for 'flipper_length_mm'
penguins_clean = penguins.dropna(subset=['flipper_length_mm'])

# Create an empty figure
fig = go.Figure()

# Define colors for each species
species_colors = {
    "Adelie": "blue",
    "Chinstrap": "green",
    "Gentoo": "orange"
}

# Iterate over each species
for species, color in species_colors.items():
    species_data = penguins_clean[penguins_clean['species'] == species]['flipper_length_mm']

    # Location statistics
    mean = species_data.mean()
    median = species_data.median()

    # Scale statistics
    min_val = species_data.min()
    max_val = species_data.max()
    q1 = species_data.quantile(0.25)
    q3 = species_data.quantile(0.75)
    std_dev = species_data.std()
    lower_2std = mean - 2 * std_dev
    upper_2std = mean + 2 * std_dev

    # Add histogram for the current species
    fig.add_trace(go.Histogram(x=species_data, name=f"{species} Flipper Length", opacity=0.6, marker_color=color, nbinsx=30))

    # Add vertical lines for mean and median
    fig.add_vline(x=mean, line=dict(color=color, width=2, dash="dash"), annotation_text=f'{species} Mean', annotation_position="top left")
    fig.add_vline(x=median, line=dict(color=color, width=2, dash="dot"), annotation_text=f'{species} Median', annotation_position="top right")

    # Add vertical rectangle for range (min to max)
    fig.add_vrect(x0=min_val, x1=max_val, fillcolor=color, opacity=0.2, line_width=0, annotation_text=f'{species} Range', annotation_position="bottom left")

    # Add vertical rectangle for IQR (Q1 to Q3)
    fig.add_vrect(x0=q1, x1=q3, fillcolor=color, opacity=0.4, line_width=0, annotation_text=f'{species} IQR', annotation_position="bottom right")

    # Add vertical rectangle for 2 standard deviations
    fig.add_vrect(x0=lower_2std, x1=upper_2std, fillcolor=color, opacity=0.1, line_width=0, annotation_text=f'{species} ±2σ', annotation_position="top right")

# Update layout and axis labels
fig.update_layout(
    title="Flipper Length Distribution by Species with Location and Scale Annotations",
    xaxis_title="Flipper Length (mm)",
    yaxis_title="Count",
    barmode="overlay"
)

# Show the plot
fig.show()

import plotly.graph_objects as go
import seaborn as sns
import numpy as np

# Load the penguins dataset
penguins = sns.load_dataset("penguins")

# Drop rows with missing values for 'flipper_length_mm'
penguins_clean = penguins.dropna(subset=['flipper_length_mm'])

# Define colors for each species
species_colors = {
    "Adelie": "blue",
    "Chinstrap": "green",
    "Gentoo": "orange"
}

# Iterate over each species and create separate histograms
for species, color in species_colors.items():
    species_data = penguins_clean[penguins_clean['species'] == species]['flipper_length_mm']

    # Location statistics
    mean = species_data.mean()
    median = species_data.median()

    # Scale statistics
    min_val = species_data.min()
    max_val = species_data.max()
    q1 = species_data.quantile(0.25)
    q3 = species_data.quantile(0.75)
    std_dev = species_data.std()
    lower_2std = mean - 2 * std_dev
    upper_2std = mean + 2 * std_dev

    # Create a new figure for each species
    fig = go.Figure()

    # Add histogram for the current species
    fig.add_trace(go.Histogram(x=species_data, name=f"{species} Flipper Length", opacity=0.6, marker_color=color, nbinsx=30))

    # Add vertical lines for mean and median
    fig.add_vline(x=mean, line=dict(color=color, width=2, dash="dash"), annotation_text=f'Mean: {mean:.2f}', annotation_position="top left")
    fig.add_vline(x=median, line=dict(color=color, width=2, dash="dot"), annotation_text=f'Median: {median:.2f}', annotation_position="top right")

    # Add vertical rectangle for range (min to max)
    fig.add_vrect(x0=min_val, x1=max_val, fillcolor=color, opacity=0.2, line_width=0, annotation_text=f'Range: {min_val:.2f} - {max_val:.2f}', annotation_position="bottom left")

    # Add vertical rectangle for IQR (Q1 to Q3)
    fig.add_vrect(x0=q1, x1=q3, fillcolor=color, opacity=0.4, line_width=0, annotation_text=f'IQR: {q1:.2f} - {q3:.2f}', annotation_position="bottom right")

    # Add vertical rectangle for 2 standard deviations
    fig.add_vrect(x0=lower_2std, x1=upper_2std, fillcolor=color, opacity=0.1, line_width=0, annotation_text=f'±2σ: {lower_2std:.2f} - {upper_2std:.2f}', annotation_position="top right")

    # Update layout and axis labels
    fig.update_layout(
        title=f"Flipper Length Distribution for {species} Penguins",
        xaxis_title="Flipper Length (mm)",
        yaxis_title="Count",
        barmode="overlay"
    )

    # Show the plot for the current species
    fig.show()

# Question 2 - code that chatgpt gave me directly

import seaborn as sns
import matplotlib.pyplot as plt
import numpy as np

# Load the penguins dataset
penguins = sns.load_dataset("penguins")

# Drop rows with missing values for 'flipper_length_mm'
penguins_clean = penguins.dropna(subset=['flipper_length_mm'])

# Set up the plotting area with 3 plots in a row
fig, axes = plt.subplots(1, 3, figsize=(18, 6))

# Define species list and colors for each species
species_list = ['Adelie', 'Chinstrap', 'Gentoo']
species_colors = ['blue', 'green', 'orange']

# Iterate over each species and create KDE plots
for i, species in enumerate(species_list):
    species_data = penguins_clean[penguins_clean['species'] == species]['flipper_length_mm']
    
    # Calculate statistics
    mean = species_data.mean()
    median = species_data.median()
    min_val = species_data.min()
    max_val = species_data.max()
    q1 = species_data.quantile(0.25)
    q3 = species_data.quantile(0.75)
    std_dev = species_data.std()
    lower_2std = mean - 2 * std_dev
    upper_2std = mean + 2 * std_dev

    # Plot KDE for the current species
    sns.kdeplot(species_data, ax=axes[i], color=species_colors[i], fill=True, label=f'{species} KDE')

    # Add vertical lines for mean and median
    axes[i].axvline(mean, color='blue', linestyle='--', label=f'Mean: {mean:.2f}')
    axes[i].axvline(median, color='green', linestyle='-.', label=f'Median: {median:.2f}')

    # Add shaded areas for range (min to max), IQR (Q1 to Q3), and ±2 standard deviations
    axes[i].axvspan(min_val, max_val, color='purple', alpha=0.2, label=f'Range: {min_val:.2f} - {max_val:.2f}')
    axes[i].axvspan(q1, q3, color='orange', alpha=0.4, label=f'IQR: {q1:.2f} - {q3:.2f}')
    axes[i].axvspan(lower_2std, upper_2std, color='red', alpha=0.1, label=f'±2σ: {lower_2std:.2f} - {upper_2std:.2f}')

    # Set plot titles and labels
    axes[i].set_title(f'{species} Penguins Flipper Length KDE')
    axes[i].set_xlabel('Flipper Length (mm)')
    axes[i].set_ylabel('Density')

    # Add legend to each plot
    axes[i].legend(loc='upper right')

# Adjust layout for better readability
plt.tight_layout()

# Show the plot
plt.show()

# Question 4

from scipy import stats
import plotly.graph_objects as go
from plotly.subplots import make_subplots
import numpy as np

n = 1500
data1 = stats.uniform.rvs(0, 10, size=n)
data2 = stats.norm.rvs(5, 1.5, size=n)
data3 = np.r_[stats.norm.rvs(2, 0.25, size=int(n/2)), stats.norm.rvs(8, 0.5, size=int(n/2))]
data4 = stats.norm.rvs(6, 0.5, size=n)

fig = make_subplots(rows=1, cols=4)

fig.add_trace(go.Histogram(x=data1, name='A', nbinsx=30, marker=dict(line=dict(color='black', width=1))), row=1, col=1)
fig.add_trace(go.Histogram(x=data2, name='B', nbinsx=15, marker=dict(line=dict(color='black', width=1))), row=1, col=2)
fig.add_trace(go.Histogram(x=data3, name='C', nbinsx=45, marker=dict(line=dict(color='black', width=1))), row=1, col=3)
fig.add_trace(go.Histogram(x=data4, name='D', nbinsx=15, marker=dict(line=dict(color='black', width=1))), row=1, col=4)

fig.update_layout(height=300, width=750, title_text="Row of Histograms")
fig.update_xaxes(title_text="A", row=1, col=1)
fig.update_xaxes(title_text="B", row=1, col=2)
fig.update_xaxes(title_text="C", row=1, col=3)
fig.update_xaxes(title_text="D", row=1, col=4)
fig.update_xaxes(range=[-0.5, 10.5])

for trace in fig.data:
    trace.xbins = dict(start=0, end=10)
    
# This code was produced by just making requests to Microsoft Copilot
# https://github.com/pointOfive/stat130chat130/blob/main/CHATLOG/wk3/COP/SLS/0001_concise_makeAplotV1.md

fig.show() # USE `fig.show(renderer="png")` FOR ALL GitHub and MarkUs SUBMISSIONS

# Question 6

# my dataset on cheeses:

import pandas as pd

cheeses = pd.read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2024/2024-06-04/cheeses.csv')
cheeses

# Question 6

#checking for columns with lots of missing values:

cheeses.isnull().sum()

cheese                0
url                   0
milk                 36
country              11
region              332
family              698
type                 13
fat_content         939
calcium_content    1162
texture              58
rind                242
color               142
flavor               98
aroma               258
vegetarian          439
vegan               439
synonyms            893
alt_spellings      1078
producers           400
dtype: int64

# Question 6

# I want to throw out columns where more than half of the values are missing so I have asked chat to give me code to do this:

import pandas as pd

cheeses = pd.read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2024/2024-06-04/cheeses.csv')
cheeses

# Calculate the threshold for dropping columns (e.g., more than 50% missing)
threshold = len(cheeses) * 0.5

# Drop columns where the number of missing values is greater than the threshold
cheeses = cheeses.dropna(axis=1, thresh=threshold)

# I dont want all these columns, so I will drop the ones I am not interested in (also gives more data when using dropna())
# once again using chatgpt code

cheeses = cheeses[['milk', 'country', 'color']]

# now I will just use dropna() on the rest

cheeses = cheeses.dropna()

cheeses

cheeses.describe()

# Question 6

# Code as given by chatgpt

import pandas as pd
import plotly.express as px

# Load the dataset
cheeses = pd.read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2024/2024-06-04/cheeses.csv')

# Drop columns where more than half of the values are missing
threshold = len(cheeses) * 0.5
cheeses = cheeses.dropna(axis=1, thresh=threshold)

# Keep only the relevant columns
cheeses = cheeses[['milk', 'country', 'color']]

# Drop rows with any missing values
cheeses = cheeses.dropna()

# Create an interactive boxplot
fig = px.box(cheeses, x='milk', y='color', title='Boxplot of Milk Types vs. Color',
              labels={'milk': 'Type of Milk', 'color': 'Color'})

# Show the plot
fig.show()

# Question 6

# again code by chatgpt

import pandas as pd
import plotly.express as px

# Load the dataset
cheeses = pd.read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2024/2024-06-04/cheeses.csv')

# Drop columns where more than half of the values are missing
threshold = len(cheeses) * 0.5
cheeses = cheeses.dropna(axis=1, thresh=threshold)

# Keep only the relevant columns
cheeses = cheeses[['milk', 'country', 'type', 'rind', 'color']]

# Drop rows with any missing values
cheeses = cheeses.dropna()

# Create an interactive histogram of the number of cheeses produced in each country
fig = px.histogram(cheeses, x='country', title='Frequency of Cheeses Produced by Country',
                   labels={'country': 'Country'}, 
                   color='country',  # Optional: color by country
                   text_auto=True)   # Show counts on bars

# Update layout for better visualization
fig.update_layout(xaxis_title='Country',
                  yaxis_title='Number of Cheeses',
                  xaxis_tickangle=-45)  # Rotate x-axis labels for better visibility

# Show the plot
fig.show()

# Question 7

import plotly.io as pio

pio.templates.default = "plotly_dark"

import plotly.express as px
df = px.data.gapminder()
px.scatter(df, x="gdpPercap", y="lifeExp", animation_frame="year", animation_group="country",
           size="pop", color="continent", hover_name="country",
           log_x=True, size_max=55, range_x=[100,100000], range_y=[25,90])

# Question 8

import plotly.io as pio

pio.templates.default = "plotly_dark"

bn = pd.read_csv('https://raw.githubusercontent.com/hadley/data-baby-names/master/baby-names.csv')
bn['name'] = bn['name']+" "+bn['sex'] # make identical boy and girl names distinct
bn['rank'] = bn.groupby('year')['percent'].rank(ascending=False)
bn = bn.sort_values(['name','year'])
# the next three lines create the increaes or decrease in name prevalence from the last year 
bn['percent change'] = bn['percent'].diff()
new_name = [True]+list(bn.name[:-1].values!=bn.name[1:].values)
bn.loc[new_name,'percentage change'] = bn.loc[new_name,'percent'] 
bn = bn.sort_values('year')
bn = bn[bn.percent>0.001] # restrict to "common" names

import plotly.express as px
df = px.data.gapminder()
fig = px.scatter(df, x="percent change", y="rank", animation_frame="year", animation_group="name",
           size="percent", color="continent", hover_name="name",
           size_max=50, range_x=[-0.005,0.005])

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
Cell In[13], line 20
     18 import plotly.express as px
     19 df = px.data.gapminder()
---> 20 fig = px.scatter(df, x="percent change", y="rank", animation_frame="year", animation_group="name",
     21            size="percent", color="continent", hover_name="name",
     22            size_max=50, range_x=[-0.005,0.005])

File /opt/conda/lib/python3.11/site-packages/plotly/express/_chart_types.py:66, in scatter(data_frame, x, y, color, symbol, size, hover_name, hover_data, custom_data, text, facet_row, facet_col, facet_col_wrap, facet_row_spacing, facet_col_spacing, error_x, error_x_minus, error_y, error_y_minus, animation_frame, animation_group, category_orders, labels, orientation, color_discrete_sequence, color_discrete_map, color_continuous_scale, range_color, color_continuous_midpoint, symbol_sequence, symbol_map, opacity, size_max, marginal_x, marginal_y, trendline, trendline_options, trendline_color_override, trendline_scope, log_x, log_y, range_x, range_y, render_mode, title, template, width, height)
     12 def scatter(
     13     data_frame=None,
     14     x=None,
   (...)
     60     height=None,
     61 ) -> go.Figure:
     62     """
     63     In a scatter plot, each row of `data_frame` is represented by a symbol
     64     mark in 2D space.
     65     """
---> 66     return make_figure(args=locals(), constructor=go.Scatter)

File /opt/conda/lib/python3.11/site-packages/plotly/express/_core.py:2090, in make_figure(args, constructor, trace_patch, layout_patch)
   2087 layout_patch = layout_patch or {}
   2088 apply_default_cascade(args)
-> 2090 args = build_dataframe(args, constructor)
   2091 if constructor in [go.Treemap, go.Sunburst, go.Icicle] and args["path"] is not None:
   2092     args = process_dataframe_hierarchy(args)

File /opt/conda/lib/python3.11/site-packages/plotly/express/_core.py:1492, in build_dataframe(args, constructor)
   1489     args["color"] = None
   1490 # now that things have been prepped, we do the systematic rewriting of `args`
-> 1492 df_output, wide_id_vars = process_args_into_dataframe(
   1493     args, wide_mode, var_name, value_name
   1494 )
   1496 # now that `df_output` exists and `args` contains only references, we complete
   1497 # the special-case and wide-mode handling by further rewriting args and/or mutating
   1498 # df_output
   1500 count_name = _escape_col_name(df_output, "count", [var_name, value_name])

File /opt/conda/lib/python3.11/site-packages/plotly/express/_core.py:1213, in process_args_into_dataframe(args, wide_mode, var_name, value_name)
   1211         if argument == "index":
   1212             err_msg += "\n To use the index, pass it in directly as `df.index`."
-> 1213         raise ValueError(err_msg)
   1214 elif length and len(df_input[argument]) != length:
   1215     raise ValueError(
   1216         "All arguments should have the same length. "
   1217         "The length of column argument `df[%s]` is %d, whereas the "
   (...)
   1224         )
   1225     )

ValueError: Value of 'x' is not the name of a column in 'data_frame'. Expected one of ['country', 'continent', 'year', 'lifeExp', 'pop', 'gdpPercap', 'iso_alpha', 'iso_num'] but received: percent change

# Question 8

import pandas as pd
import plotly.express as px

# Load the baby names dataset
bn = pd.read_csv('https://raw.githubusercontent.com/hadley/data-baby-names/master/baby-names.csv')

# Make identical boy and girl names distinct by appending the sex
bn['name'] = bn['name'] + " " + bn['sex']

# Calculate the rank of names within each year based on 'percent'
bn['rank'] = bn.groupby('year')['percent'].rank(ascending=False)

# Sort the dataset by 'name' and 'year'
bn = bn.sort_values(['name', 'year'])

# Calculate the percent change in name prevalence from the last year
bn['percent change'] = bn['percent'].diff()

# Identify when the name changes
new_name = [True] + list(bn.name[:-1].values != bn.name[1:].values)
bn.loc[new_name, 'percent change'] = bn.loc[new_name, 'percent']

# Restrict to "common" names where the percent is greater than 0.001
bn = bn[bn['percent'] > 0.001]

# Sort by year to ensure proper animation sequencing
bn = bn.sort_values('year')

# Create the interactive animated scatter plot
fig = px.scatter(bn, x="percent change", y="rank", 
                 animation_frame="year", animation_group="name", 
                 size="percent", color="sex", hover_name="name", 
                 size_max=50, range_x=[-0.005, 0.005])

# Reverse the y-axis to put rank 1 at the top
fig.update_yaxes(autorange='reversed')

# Show the plot
fig.show()  # Use 'renderer="png"' for GitHub and MarkUs submissions

	species	island	bill_length_mm	bill_depth_mm	flipper_length_mm	body_mass_g	sex
0	Adelie	Torgersen	39.1	18.7	181.0	3750.0	MALE
1	Adelie	Torgersen	39.5	17.4	186.0	3800.0	FEMALE
2	Adelie	Torgersen	40.3	18.0	195.0	3250.0	FEMALE
3	Adelie	Torgersen	NaN	NaN	NaN	NaN	NaN
4	Adelie	Torgersen	36.7	19.3	193.0	3450.0	FEMALE
...	...	...	...	...	...	...	...
339	Gentoo	Biscoe	NaN	NaN	NaN	NaN	NaN
340	Gentoo	Biscoe	46.8	14.3	215.0	4850.0	FEMALE
341	Gentoo	Biscoe	50.4	15.7	222.0	5750.0	MALE
342	Gentoo	Biscoe	45.2	14.8	212.0	5200.0	FEMALE
343	Gentoo	Biscoe	49.9	16.1	213.0	5400.0	MALE

	cheese	url	milk	country	region	family	type	fat_content	calcium_content	texture	rind	color	flavor	aroma	vegetarian	vegan	synonyms	alt_spellings	producers
0	Aarewasser	https://www.cheese.com/aarewasser/	cow	Switzerland	NaN	NaN	semi-soft	NaN	NaN	buttery	washed	yellow	sweet	buttery	False	False	NaN	NaN	Jumi
1	Abbaye de Belloc	https://www.cheese.com/abbaye-de-belloc/	sheep	France	Pays Basque	NaN	semi-hard, artisan	NaN	NaN	creamy, dense, firm	natural	yellow	burnt caramel	lanoline	True	False	Abbaye Notre-Dame de Belloc	NaN	NaN
2	Abbaye de Belval	https://www.cheese.com/abbaye-de-belval/	cow	France	NaN	NaN	semi-hard	40-46%	NaN	elastic	washed	ivory	NaN	aromatic	False	False	NaN	NaN	NaN
3	Abbaye de Citeaux	https://www.cheese.com/abbaye-de-citeaux/	cow	France	Burgundy	NaN	semi-soft, artisan, brined	NaN	NaN	creamy, dense, smooth	washed	white	acidic, milky, smooth	barnyardy, earthy	False	False	NaN	NaN	NaN
4	Abbaye de Tamié	https://www.cheese.com/tamie/	cow	France	Savoie	NaN	soft, artisan	NaN	NaN	creamy, open, smooth	washed	white	fruity, nutty	perfumed, pungent	False	False	NaN	Tamié, Trappiste de Tamie, Abbey of Tamie	NaN
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
1182	Sveciaost	https://www.cheese.com/sveciaost/	cow	Sweden	Low-laying regions	NaN	semi-hard, brined	45%	NaN	creamy, supple	rindless	pale yellow	acidic	NaN	False	False	NaN	NaN	NaN
1183	Swag	https://www.cheese.com/swag/	goat	Australia	South Australia	NaN	fresh firm, artisan	NaN	NaN	creamy, crumbly	ash coated	white	acidic, creamy	fresh	True	False	NaN	NaN	Woodside Cheese Wrights
1184	Swaledale	https://www.cheese.com/swaledale/	sheep	England	Swaledale, North Yorkshire	NaN	hard	NaN	NaN	semi firm	NaN	yellow	smooth, sweet	floral	True	False	Swaledale Sheep Cheese	NaN	NaN
1185	Sweet Style Swiss	https://www.cheese.com/sweet-style-swiss/	NaN	Switzerland	NaN	NaN	semi-hard, artisan	NaN	NaN	firm, supple	waxed	NaN	nutty	nutty, sweet	False	False	NaN	NaN	NaN
1186	Swiss cheese	https://www.cheese.com/swiss/	cow	United States	NaN	Swiss Cheese	hard, artisan, processed	7.8 g/100g	NaN	firm	rindless	pale yellow	nutty, sweet	NaN	True	False	American Swiss Cheese	NaN	Various

	milk	country	color
0	cow	Switzerland	yellow
1	sheep	France	yellow
2	cow	France	ivory
3	cow	France	white
4	cow	France	white
...	...	...	...
1180	goat	United States	ivory
1182	cow	Sweden	pale yellow
1183	goat	Australia	white
1184	sheep	England	yellow
1186	cow	United States	pale yellow

	milk	country	color
count	1010	1010	1010
unique	20	73	17
top	cow	United States	white
freq	609	272	271